US20160343379A1 - System and method for detecting synthetic speaker verification - Google Patents

System and method for detecting synthetic speaker verification Download PDF

Info

Publication number
US20160343379A1
US20160343379A1 US15/229,376 US201615229376A US2016343379A1 US 20160343379 A1 US20160343379 A1 US 20160343379A1 US 201615229376 A US201615229376 A US 201615229376A US 2016343379 A1 US2016343379 A1 US 2016343379A1
Authority
US
United States
Prior art keywords
plurality
speech samples
speech
sample
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
US15/229,376
Other versions
US9812133B2 (en
Inventor
Horst J. Schroeter
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nuance Communications Inc
Original Assignee
AT&T Intellectual Property I LP
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to US12/101,482 priority Critical patent/US8504365B2/en
Priority to US13/959,305 priority patent/US8805685B2/en
Priority to US14/454,104 priority patent/US9142218B2/en
Priority to US14/859,449 priority patent/US9412382B2/en
Application filed by AT&T Intellectual Property I LP filed Critical AT&T Intellectual Property I LP
Assigned to AT&T LABS, INC. reassignment AT&T LABS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: SCHROETER, HORST
Priority to US15/229,376 priority patent/US9812133B2/en
Publication of US20160343379A1 publication Critical patent/US20160343379A1/en
Assigned to AT&T INTELLECTUAL PROPERTY I, L.P. reassignment AT&T INTELLECTUAL PROPERTY I, L.P. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: AT&T LABS, INC.
Assigned to NUANCE COMMUNICATIONS, INC. reassignment NUANCE COMMUNICATIONS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: AT&T INTELLECTUAL PROPERTY I, L.P.
Publication of US9812133B2 publication Critical patent/US9812133B2/en
Application granted granted Critical
Application status is Active legal-status Critical
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00Speaker identification or verification
    • G10L17/22Interactive procedures; Man-machine interfaces
    • G10L17/24Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00Speaker identification or verification
    • G10L17/005Speaker recognisers specially adapted for particular applications
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00Speaker identification or verification
    • G10L17/04Training, enrolment or model building
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00Speaker identification or verification
    • G10L17/06Decision making techniques; Pattern matching strategies
    • G10L17/08Use of distortion metrics or a particular distance between probe pattern and reference templates
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00Speaker identification or verification
    • G10L17/20Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions

Abstract

Disclosed herein are systems, methods, and tangible computer readable-media for detecting synthetic speaker verification. The method comprises receiving a plurality of speech samples of the same word or phrase for verification, comparing each of the plurality of speech samples to each other, denying verification if the plurality of speech samples demonstrate little variance over time or are the same, and verifying the plurality of speech samples if the plurality of speech samples demonstrates sufficient variance over time. One embodiment further adds that each of the plurality of speech samples is collected at different times or in different contexts. In other embodiments, variance is based on a pre-determined threshold or the threshold for variance is adjusted based on a need for authentication certainty. In another embodiment, if the initial comparison is inconclusive, additional speech samples are received.

Description

    PRIORITY INFORMATION
  • The present application is a continuation of U.S. patent application Ser. No. 14/859,449, filed Sep. 21, 2015, which is a continuation of U.S. patent application Ser. No. 14/454,104, filed Aug. 7, 2014, now U.S. Pat. No. 9,142,218, issued Sep. 22, 2015, which is a continuation of U.S. patent application Ser. No. 13/959,305, filed Aug. 5, 2013, now U.S. Pat. No. 8,805,685, issued Aug. 12, 2014, which is a continuation of U.S. patent application Ser. No. 12/101,482, filed Apr. 11, 2008, now U.S. Pat. No. 8,504,365, issued Aug. 6, 2013, the contents of which is incorporated herein by reference in its entirety.
  • BACKGROUND OF THE INVENTION
  • 1. Field of the Invention
  • The present invention relates to speaker verification and more specifically to synthetic attempts at speaker verification.
  • 2. Introduction
  • Speaker and speech authentication systems are becoming more prevalent as speech recognition technology has improved and becomes available in cheaper, more reliable forms. As a biometric identification process, speech authentication systems are easy for users to interact with because there is nothing to forget or lose. Other biometric identification means exist, such as fingerprints or retinal scans, but hardware to accept such inputs are not widespread while microphones capable of receiving a speech sample are very widespread and integrated into many devices.
  • While using speech as a means of identification can be convenient for businesses and users, speech synthesis technology has also improved as a corollary of speech recognition. Speech synthesis technology can be used to defeat or trick speech authentication systems, lessening their effectiveness. While technology for recording someone's voice saying a particular password has been available for decades, that deceptive approach is simple enough to circumvent by requiring a different word to be spoken for speech identification so the would-be deceiver needs to not only record a speech sample, but also predict which word will be required for authentication.
  • Speech recognition systems may require any word to be spoken, thereby defeating the traditional attack of a pre-recorded speech library. Speech synthesis systems can replicate practically any voice, and presumably, any word or phrase. Speech recognition systems are unable to detect between the original, authentic speech and synthetic speech, potentially leading to confusion and security breaches.
  • Accordingly, what is needed in the art is a way of detecting speech synthesis-based attempted breaches on speech recognition and authentication systems.
  • SUMMARY
  • Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The features and advantages of the invention may be realized and obtained by means of the instruments and combinations particularly pointed out in the appended claims. These and other features of the present invention will become more fully apparent from the following description and appended claims, or may be learned by the practice of the invention as set forth herein.
  • Disclosed are systems, methods and computer-readable media for detecting synthetic speaker verification. The system of the present disclosure is based on receiving a plurality of speech samples of the same word or phrase for verification, comparing each of the plurality of speech samples to each other, denying verification if the plurality of speech samples demonstrates little variance over time or are the same, and verifying the plurality of speech samples if the plurality of speech samples demonstrates sufficient variance over time.
  • The systems, methods, and computer-readable media may be compatible for use with speech recognition based biometric verification. In one embodiment, each of the plurality of speech samples is collected at different times or in different contexts. In other embodiments, variance is based on a pre-determined threshold which is adjusted based on a need for authentication certainty or security. In a third embodiment, additional speech samples are received for further comparison if the initial comparison is inconclusive.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • In order to describe the manner in which the above-recited and other advantages and features of the invention can be obtained, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. Understanding that these drawings depict only exemplary embodiments of the invention and are not therefore to be considered to be limiting of its scope, the invention will be described and explained with additional specificity and detail through the use of the accompanying drawings in which:
  • FIG. 1 illustrates an example system embodiment;
  • FIG. 2 illustrates a method embodiment for detecting synthetic speaker verification;
  • FIG. 3 illustrates an exemplary system for allowing or denying access;
  • FIG. 4 illustrates an exemplary device as part of the system of FIG. 3; and
  • FIG. 5 illustrates a sample database of speech samples.
  • DETAILED DESCRIPTION
  • Various embodiments of the invention are discussed in detail below. While specific implementations are discussed, it should be understood that this is done for illustration purposes only. A person skilled in the relevant art will recognize that other components and configurations may be used without parting from the spirit and scope of the invention.
  • With reference to FIG. 1, an exemplary system includes a general-purpose computing device 100, including a processing unit (CPU) 120 and a system bus 110 that couples various system components including the system memory such as read only memory (ROM) 140 and random access memory (RAM) 150 to the processing unit 120. Other system memory 130 may be available for use as well. It can be appreciated that the invention may operate on a computing device with more than one CPU 120 or on a group or cluster of computing devices networked together to provide greater processing capability. The system bus 110 may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. A basic input/output (BIOS) stored in ROM 140 or the like, may provide the basic routine that helps to transfer information between elements within the computing device 100, such as during start-up. The computing device 100 further includes storage devices such as a hard disk drive 160, a magnetic disk drive, an optical disk drive, tape drive or the like. The storage device 160 is connected to the system bus 110 by a drive interface. The drives and the associated computer readable media provide nonvolatile storage of computer readable instructions, data structures, program modules and other data for the computing device 100. In one aspect, a hardware module that performs a particular function includes the software component stored in a computer-readable medium in connection with the necessary hardware components, such as the CPU, bus, display, and so forth, to carry out the function. The basic components are known to those of skill in the art and appropriate variations are contemplated depending on the type of device, such as whether the device is a small, handheld computing device, a desktop computer, or a computer server.
  • Although the exemplary environment described herein employs the hard disk, it should be appreciated by those skilled in the art that other types of computer readable media which can store data that are accessible by a computer, such as magnetic cassettes, flash memory cards, digital versatile disks, cartridges, random access memories (RAMs), read only memory (ROM), a cable or wireless signal containing a bit stream and the like, may also be used in the exemplary operating environment.
  • To enable user interaction with the computing device 100, an input device 190 represents any number of input mechanisms, such as a microphone for speech, a touch-sensitive screen for gesture or graphical input, keyboard, mouse, motion input, speech and so forth. The input may be used by the presenter to indicate the beginning of a speech search query. The device output 170 can also be one or more of a number of output mechanisms known to those of skill in the art. In some instances, multimodal systems enable a user to provide multiple types of input to communicate with the computing device 100. The communications interface 180 generally governs and manages the user input and system output. There is no restriction on the invention operating on any particular hardware arrangement and therefore the basic features here may easily be substituted for improved hardware or firmware arrangements as they are developed.
  • For clarity of explanation, the illustrative system embodiment is presented as comprising individual functional blocks (including functional blocks labeled as a “processor”). The functions these blocks represent may be provided through the use of either shared or dedicated hardware, including, but not limited to, hardware capable of executing software. For example the functions of one or more processors presented in FIG. 1 may be provided by a single shared processor or multiple processors. (Use of the term “processor” should not be construed to refer exclusively to hardware capable of executing software.) Illustrative embodiments may comprise microprocessor and/or digital signal processor (DSP) hardware, read-only memory (ROM) for storing software performing the operations discussed below, and random access memory (RAM) for storing results. Very large scale integration (VLSI) hardware embodiments, as well as custom VLSI circuitry in combination with a general purpose DSP circuit, may also be provided.
  • The logical operations of the various embodiments are implemented as: (1) a sequence of computer implemented steps, operations, or procedures running on a programmable circuit within a general use computer, (2) a sequence of computer implemented steps, operations, or procedures running on a specific-use programmable circuit; and/or (3) interconnected machine modules or program engines within the programmable circuits.
  • FIG. 2 illustrates a method embodiment for adaptive media playback. The method may be practiced on any system or device depending on the particular application. First, the method receives a plurality of speech samples of the same word or phrase for verification (202). One aspect of the method is speech samples as short as one word. One common example is a user's first name. While a name is a possible requested speech sample, other non-personal words may also be desirable because a would-be deceiver could easily capture speech samples of a common word like a user's first name. In order to avoid false positives resulting from something as simple as a tape recorded speech sample as well as synthetic speech, longer or more obscure words may be desired. For example, a randomly generated password is requested from the user like “granite”, “earwig”, or “nimbus”.
  • The same principles that apply to words also apply to phrases. It would be simple to record common phrases like “hello, how are you?”, whereas a more obscure phrase like “clowns infrequently scare children” would be more difficult.
  • In one aspect of the method, each of the plurality of speech samples is collected at different times or in different contexts. For example, an enrollment period and verification period is established in a speaker verification scheme. In an enrollment period, a user is asked to say multiple different words or phrases, and in a later verification period, the user is asked to repeat one or more of the different words or phrases. One or more speech samples are gathered in both the enrollment period and the verification period. In another embodiment, both speech samples are requested from the user one immediately after the other, effectively eliminating the enrollment period. For example, the system asks a user to say “swordfish” twice in a row, each instance of the word being a separate speech sample. A minimum of two speech samples is received for comparison. More speech samples can be received various times.
  • Second, the method compares each of the plurality of speech samples to each other 204. Third, the method denies verification if the plurality of speech samples demonstrates little variance over time or are the same 206. Those of skill in the art will understand the scope and process of identifying the level of variance between the speech samples. Fourth, the method verifies the plurality of speech samples if the plurality of speech samples demonstrates sufficient variance over time 208.
  • Comparing the speech samples to each other is a check if the speech samples are too similar (or even identical). The subtle flaws and inconsistencies of human speech as well as the repetitive nature of machine-based speech synthesis allow for such a comparison. Some examples of sources of flaws and inconsistencies of human speech include colds, aging of the speaker, evolving accents, and prosodic variations based on the person's mood, the time of day, context of the speech sample, background noise, etc. If the speech samples are too similar or identical, the speech samples are identified as synthetic. In other words, slight or small variations are expected in different voice samples of the same person.
  • In one aspect, variance is based on a pre-determined threshold. The threshold is determined based on security or other needs. In a highly secure environment, such as a military installation, a tighter threshold is employed. In a lower security environment, such as using a voice sample to unlock a cell phone in order to place a call, the threshold is much lower so users do not get annoyed or frustrated with a stricter threshold. In other words, the pre-determined threshold for variance is adjusted based on a need for authentication certainty.
  • One embodiment addresses the situation where, in some cases, an initial comparison between speech samples is inconclusive. The variance may be below the threshold, but close. The variance may be off the charts because a subsequent speech sample may be of a different word or phrase than previous speech samples. If the initial comparison is inconclusive for any reason, additional speech samples are received for further analysis. For example, a user could be prompted “Speech verification was inconclusive. Please repeat the pass phrase ‘swordfish.’”
  • FIG. 3 illustrates an exemplary system for allowing or denying access based on checking if a speech sample is synthetic or not. This system adds to the conventional voice recognition authentication scheme the feature of checking if a purported matching speech sample is merely synthetically generated. First, the system gathers a speech sample from a user 300 through a microphone 302. The system performs this step multiple times to gather multiple speech samples. The collected speech samples are stored in a speech sample database 304. The system compares speech samples from a user using a comparison processor 306 to confirm that the user is the authentic. The comparison processor is designed to compare speech samples to determine if they are from the same person. If the speech samples are determined to be from the same person, the system compares the speech samples again to determine if they are too similar or are exactly the same. If so, then the speech samples are likely to be synthetically generated. The comparison processor retrieves from the certainty level database 310 one or more parameters for determining how similar is too similar. The certainty level database contains parameters for multiple tasks or voices. For example, the parameters regulating access to a janitorial closet are looser than those accessing the vault or the parameters for comparing the CEO's voice are tighter than those for comparing a temporary worker's voice. In one aspect, the comparison processor retrieves multiple certainty levels and either combines them into one comparison or performs multiple comparisons with different parameters.
  • When the comparison processor determines that the speech samples are a match and the match is not a synthetically generated match, the comparison processor communicates with an access mechanism 308. Access mechanism implementations include physical, electronic, and computer, such as a door lock, an electric fence, a computer login prompt, or any other device which can allow or deny access. The system illustrated contains one access mechanism, but multiple access mechanisms are also possible. In one aspect of the system, the certainty level database 310 contains unique parameters for each access mechanism 308.
  • FIG. 4 illustrates an exemplary device 400 as part of the system of FIG. 3. The device illustrated is designed to allow or deny passage through a doorway. The device includes a speaker 402 to communicate with a user. One situation where the device communicates with a user is prompting the user to say a word or phrase in order to gather a speech sample. The device can communicate in other ways with users, but a speaker is desirable because users are already speaking, and continuing the speech interface is a natural progression. The device has an integrated microphone 404 to capture speech samples. The device of FIG. 4 can either integrate within itself all or some of the speech samples database, the comparison processor, and the certainty level database in FIG. 3 or it can communicate with all or some of them remotely. When a speech sample is verified as authentic and non-synthetic, the access mechanism 406 is unlocked and allows passage through the door. The device may be used in locations where noise is not desired or the device may encounter users who are deaf In these cases, a visual display 408 is included to communicate with the user. Typically such communications will elicit a speech sample from the user, inform the user that access is granted, or inform the user that access is denied, but other communications are contemplated.
  • FIG. 5 illustrates a sample database of speech samples 304, as shown in FIG. 3. The speech sample database 304 contains three sub-databases 504 a, 504 b, 504 c for each of user 1, user 2, and user 3. Each sub-database contains speech samples for individual users 506 a, 506 b, 506 c. For example, different contexts may require different stores of speech for a respective user. For example, a different speech file may be created for each location where a user is—such as home, work and traveling on a train. As the system gathers speech samples, they are stored in their respective database. As synthetic speech samples are detected, they are stored in their respective database and flagged as non-authentic. If the same synthetic speech sample is received in the future, the system will be able to quickly determine that it was previously detected as synthetic and deny access.
  • Embodiments within the scope of the present invention may also include computer-readable media for carrying or having computer-executable instructions or data structures stored thereon. Such computer-readable media can be any available media that can be accessed by a general purpose or special purpose computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code means in the form of computer-executable instructions or data structures. When information is transferred or provided over a network or another communications connection (either hardwired, wireless, or combination thereof) to a computer, the computer properly views the connection as a computer-readable medium. A “tangible” computer-readable medium expressly excludes software per se (not stored on a tangible medium) and a wireless, air interface. Thus, any such connection is properly termed a computer-readable medium. Combinations of the above should also be included within the scope of the computer-readable media.
  • Computer-executable instructions include, for example, instructions and data which cause a general purpose computer, special purpose computer, or special purpose processing device to perform a certain function or group of functions. Computer-executable instructions also include program modules that are executed by computers in stand-alone or network environments. Generally, program modules include routines, programs, objects, components, and data structures, etc. that perform particular tasks or implement particular abstract data types. Computer-executable instructions, associated data structures, and program modules represent examples of the program code means for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps.
  • Those of skill in the art will appreciate that other embodiments of the invention may be practiced in network computing environments with many types of computer system configurations, including personal computers, hand-held devices, multi-processor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, and the like. Embodiments may also be practiced in distributed computing environments where tasks are performed by local and remote processing devices that are linked (either by hardwired links, wireless links, or by a combination thereof) through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.
  • The various embodiments described above are provided by way of illustration only and should not be construed to limit the invention. For example, the processes described herein may have application in online banking, voice authorization for confidential or top-secret areas, or other areas where reliable biometric authentication is desired. Those skilled in the art will readily recognize various modifications and changes that may be made to the present invention without following the example embodiments and applications illustrated and described herein, and without departing from the true spirit and scope of the present invention.

Claims (20)

I claim:
1. A method comprising:
receiving, via a processor and from a user, a plurality of speech samples of a same word, wherein the plurality of speech samples of the same word comprises a current speech sample and a plurality of previously recorded speech samples; and
enrolling the user in a speech verification system based at least in part on a comparison of a first sample in the plurality of speech samples with a second sample in the plurality of speech samples.
2. The method of claim 1, wherein the first sample of the plurality of speech samples and the second sample in the plurality of speech samples are each associated with a distinct location.
3. The method of claim 1, wherein the comparison comprises a comparison of each of the first sample in the plurality of speech samples and the second sample in the plurality of speech samples with other samples of the plurality of speech samples.
4. The method of claim 1, wherein the comparison results in a variance that identifies how different the first sample is from the second sample.
5. The method of claim 4, wherein when the variance is below a threshold, then not enrolling the user in the speech verification system.
6. The method of claim 5, wherein when the variance is at or above the threshold, then enrolling the user in the speech verification system.
7. The method of claim 4, wherein the variance has a range which varies based on a job of the user.
8. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, result in the processor performing operations comprising:
receiving, via a processor and from a user, a plurality of speech samples of a same word, wherein the plurality of speech samples of the same word comprises a current speech sample and a plurality of previously recorded speech samples; and
enrolling the user in a speech verification system based at least in part on a comparison of a first sample in the plurality of speech samples with a second sample in the plurality of speech samples.
9. The system of claim 8, wherein the first sample of the plurality of speech samples and the second sample in the plurality of speech samples are each associated with a distinct location.
10. The system of claim 8, wherein the comparison comprises a comparison of each of the first sample in the plurality of speech samples and the second sample in the plurality of speech samples with other samples of the plurality of speech samples.
11. The system of claim 8, wherein the comparison results in a variance that identifies how different the first sample is from the second sample.
12. The system of claim 11, wherein when the variance is below a threshold, then not enrolling the user in the speech verification system.
13. The system of claim 12, wherein when the variance is at or above the threshold, then enrolling the user in the speech verification system.
14. The system of claim 11, wherein the variance has a range which varies based on a job of the user.
15. A computer-readable storage device having instructions stored which, when executed by a computing device, result in the computing device performing operations comprising:
receiving, via a processor and from a user, a plurality of speech samples of a same word, wherein the plurality of speech samples of the same word comprises a current speech sample and a plurality of previously recorded speech samples; and
enrolling the user in a speech verification system based at least in part on a comparison of a first sample in the plurality of speech samples with a second sample in the plurality of speech samples.
16. The computer-readable storage device of claim 15, wherein the first sample of the plurality of speech samples and the second sample in the plurality of speech samples are each associated with a distinct location.
17. The computer-readable storage device of claim 15, wherein the comparison comprises a comparison of each of the first sample in the plurality of speech samples and the second sample in the plurality of speech samples with other samples of the plurality of speech samples.
18. The computer-readable storage device of claim 15, wherein the comparison results in a variance that identifies how different the first sample is from the second sample.
19. The computer-readable storage device of claim 18, wherein when the variance is below a threshold, then not enrolling the user in the speech verification system.
20. The computer-readable storage device of claim 19, wherein when the variance is at or above the threshold, then enrolling the user in the speech verification system.
US15/229,376 2008-04-11 2016-08-05 System and method for detecting synthetic speaker verification Active US9812133B2 (en)

Priority Applications (5)

Application Number Priority Date Filing Date Title
US12/101,482 US8504365B2 (en) 2008-04-11 2008-04-11 System and method for detecting synthetic speaker verification
US13/959,305 US8805685B2 (en) 2008-04-11 2013-08-05 System and method for detecting synthetic speaker verification
US14/454,104 US9142218B2 (en) 2008-04-11 2014-08-07 System and method for detecting synthetic speaker verification
US14/859,449 US9412382B2 (en) 2008-04-11 2015-09-21 System and method for detecting synthetic speaker verification
US15/229,376 US9812133B2 (en) 2008-04-11 2016-08-05 System and method for detecting synthetic speaker verification

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US15/229,376 US9812133B2 (en) 2008-04-11 2016-08-05 System and method for detecting synthetic speaker verification
US15/804,220 US20180075851A1 (en) 2008-04-11 2017-11-06 System and method for detecting synthetic speaker verification

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US14/859,449 Continuation US9412382B2 (en) 2008-04-11 2015-09-21 System and method for detecting synthetic speaker verification

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/804,220 Continuation US20180075851A1 (en) 2008-04-11 2017-11-06 System and method for detecting synthetic speaker verification

Publications (2)

Publication Number Publication Date
US20160343379A1 true US20160343379A1 (en) 2016-11-24
US9812133B2 US9812133B2 (en) 2017-11-07

Family

ID=41164711

Family Applications (6)

Application Number Title Priority Date Filing Date
US12/101,482 Active 2031-02-05 US8504365B2 (en) 2008-04-11 2008-04-11 System and method for detecting synthetic speaker verification
US13/959,305 Active US8805685B2 (en) 2008-04-11 2013-08-05 System and method for detecting synthetic speaker verification
US14/454,104 Active US9142218B2 (en) 2008-04-11 2014-08-07 System and method for detecting synthetic speaker verification
US14/859,449 Active US9412382B2 (en) 2008-04-11 2015-09-21 System and method for detecting synthetic speaker verification
US15/229,376 Active US9812133B2 (en) 2008-04-11 2016-08-05 System and method for detecting synthetic speaker verification
US15/804,220 Abandoned US20180075851A1 (en) 2008-04-11 2017-11-06 System and method for detecting synthetic speaker verification

Family Applications Before (4)

Application Number Title Priority Date Filing Date
US12/101,482 Active 2031-02-05 US8504365B2 (en) 2008-04-11 2008-04-11 System and method for detecting synthetic speaker verification
US13/959,305 Active US8805685B2 (en) 2008-04-11 2013-08-05 System and method for detecting synthetic speaker verification
US14/454,104 Active US9142218B2 (en) 2008-04-11 2014-08-07 System and method for detecting synthetic speaker verification
US14/859,449 Active US9412382B2 (en) 2008-04-11 2015-09-21 System and method for detecting synthetic speaker verification

Family Applications After (1)

Application Number Title Priority Date Filing Date
US15/804,220 Abandoned US20180075851A1 (en) 2008-04-11 2017-11-06 System and method for detecting synthetic speaker verification

Country Status (1)

Country Link
US (6) US8504365B2 (en)

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8494854B2 (en) * 2008-06-23 2013-07-23 John Nicholas and Kristin Gross CAPTCHA using challenges optimized for distinguishing between humans and machines
US9186579B2 (en) * 2008-06-27 2015-11-17 John Nicholas and Kristin Gross Trust Internet based pictorial game system and method
JP5172973B2 (en) * 2009-01-30 2013-03-27 三菱電機株式会社 Voice recognition device
US20110320201A1 (en) * 2010-06-24 2011-12-29 Kaufman John D Sound verification system using templates
US9922334B1 (en) 2012-04-06 2018-03-20 Google Llc Providing an advertisement based on a minimum number of exposures
US10152723B2 (en) 2012-05-23 2018-12-11 Google Llc Methods and systems for identifying new computers and providing matching services
WO2013186755A2 (en) * 2012-06-14 2013-12-19 David Cohen Methods circuits systems software applications and associated computer executable code for checking an implied or declared age and or gender of a party attempting to access a digital resource such as online content or a digital communication session with another party through the use of a computing device
US9110889B2 (en) 2013-04-23 2015-08-18 Facebook, Inc. Methods and systems for generation of flexible sentences in a social networking system
JP2014240884A (en) * 2013-06-11 2014-12-25 株式会社東芝 Content creation assist device, method, and program
US9257120B1 (en) 2014-07-18 2016-02-09 Google Inc. Speaker verification using co-location information
BR102014023647A2 (en) * 2014-09-24 2016-05-10 Fundacao Cpqd Ct Pesquisa E Desenvolvimento Em Tel method and system for fraud detection in speech processing-based applications
US9424841B2 (en) 2014-10-09 2016-08-23 Google Inc. Hotword detection on multiple devices
US9812128B2 (en) 2014-10-09 2017-11-07 Google Inc. Device leadership negotiation among voice interface devices
US9318107B1 (en) * 2014-10-09 2016-04-19 Google Inc. Hotword detection on multiple devices
US9466299B1 (en) 2015-11-18 2016-10-11 International Business Machines Corporation Speech source classification
US9779735B2 (en) 2016-02-24 2017-10-03 Google Inc. Methods and systems for detecting and processing speech signals
KR20190016536A (en) * 2016-06-06 2019-02-18 시러스 로직 인터내셔널 세미컨덕터 리미티드 Voice user interface
US9972320B2 (en) 2016-08-24 2018-05-15 Google Llc Hotword detection on multiple devices
US10013986B1 (en) * 2016-12-30 2018-07-03 Google Llc Data structure pooling of voice activated data packets
US10032452B1 (en) * 2016-12-30 2018-07-24 Google Llc Multimodal transmission of packetized data
US10083696B1 (en) * 2017-03-07 2018-09-25 Daon Holdings Limited Methods and systems for determining user liveness

Citations (39)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5774837A (en) * 1995-09-13 1998-06-30 Voxware, Inc. Speech coding system and method using voicing probability determination
US5806040A (en) * 1994-01-04 1998-09-08 Itt Corporation Speed controlled telephone credit card verification system
US5933803A (en) * 1996-12-12 1999-08-03 Nokia Mobile Phones Limited Speech encoding at variable bit rate
US5937381A (en) * 1996-04-10 1999-08-10 Itt Defense, Inc. System for voice verification of telephone transactions
US5940799A (en) * 1997-09-15 1999-08-17 Motorola, Inc. System and method for securing speech transactions
US5970446A (en) * 1997-11-25 1999-10-19 At&T Corp Selective noise/channel/coding models and recognizers for automatic speech recognition
US6014441A (en) * 1994-08-05 2000-01-11 Smart Tone Authentication, Inc. Method and system for generation of tone signals over a transmission channel
US6107935A (en) * 1998-02-11 2000-08-22 International Business Machines Corporation Systems and methods for access filtering employing relaxed recognition constraints
US6141644A (en) * 1998-09-04 2000-10-31 Matsushita Electric Industrial Co., Ltd. Speaker verification and speaker identification based on eigenvoices
US6272463B1 (en) * 1998-03-03 2001-08-07 Lernout & Hauspie Speech Products N.V. Multi-resolution system and method for speaker verification
US6314401B1 (en) * 1998-05-29 2001-11-06 New York State Technology Enterprise Corporation Mobile voice verification system
US6393305B1 (en) * 1999-06-07 2002-05-21 Nokia Mobile Phones Limited Secure wireless communication user identification by voice recognition
US6401066B1 (en) * 1999-11-09 2002-06-04 West Teleservices Holding Company Automated third party verification system
US20020178359A1 (en) * 2001-04-26 2002-11-28 Markus Baumeister Just-in-time authentication of users of a digital home network
US20020194005A1 (en) * 2001-03-27 2002-12-19 Lahr Roy J. Head-worn, trimodal device to increase transcription accuracy in a voice recognition system and to process unvocalized speech
US20030046083A1 (en) * 1996-11-22 2003-03-06 Edward J. Devinney User validation for information system access and transaction processing
US6546369B1 (en) * 1999-05-05 2003-04-08 Nokia Corporation Text-based speech synthesis method containing synthetic speech comparisons and updates
US6694295B2 (en) * 1998-05-25 2004-02-17 Nokia Mobile Phones Ltd. Method and a device for recognizing speech
US20040101112A1 (en) * 2002-11-26 2004-05-27 Lite-On Technology Corporation Voice identification method for cellular phone and cellular phone with voiceprint password
US20040158723A1 (en) * 2003-02-06 2004-08-12 Root David C. Methods for providing high-integrity enrollments into biometric authentication databases
US20050033581A1 (en) * 2001-02-16 2005-02-10 Foster Mark J. Dual compression voice recordation non-repudiation system
US20050096906A1 (en) * 2002-11-06 2005-05-05 Ziv Barzilay Method and system for verifying and enabling user access based on voice parameters
US20050171771A1 (en) * 1999-08-23 2005-08-04 Matsushita Electric Industrial Co., Ltd. Apparatus and method for speech coding
US6973575B2 (en) * 2001-04-05 2005-12-06 International Business Machines Corporation System and method for voice recognition password reset
US20060020459A1 (en) * 2004-07-21 2006-01-26 Carter John A System and method for immigration tracking and intelligence
US20060212407A1 (en) * 2005-03-17 2006-09-21 Lyon Dennis B User authentication and secure transaction system
US7222072B2 (en) * 2003-02-13 2007-05-22 Sbc Properties, L.P. Bio-phonetic multi-phrase speaker identity verification
US20070124144A1 (en) * 2004-05-27 2007-05-31 Johnson Richard G Synthesized interoperable communications
US20080140420A1 (en) * 2006-12-08 2008-06-12 Delta Electronics, Inc. Remote payment system
US20080208578A1 (en) * 2004-09-23 2008-08-28 Koninklijke Philips Electronics, N.V. Robust Speaker-Dependent Speech Recognition System
US7522060B1 (en) * 2005-04-25 2009-04-21 Anytransactions, Inc. Graduated sanction/progressive response system and method for automated monitoring, scheduling and notification
US20090158423A1 (en) * 2007-12-14 2009-06-18 Symbol Technologies, Inc. Locking mobile device cradle
US20090247125A1 (en) * 2008-03-27 2009-10-01 Grant Calum Anders Mckay Method and system for controlling access of computer resources of mobile client facilities
US7698566B1 (en) * 2004-07-12 2010-04-13 Sprint Spectrum L.P. Location-based voice-print authentication method and system
US7828652B2 (en) * 2004-02-12 2010-11-09 Igt Player verification method and system for remote gaming terminals
US7925887B2 (en) * 2003-05-19 2011-04-12 Intellirad Solutions Pty Ltd. Multi-parameter biometric authentication
US8255971B1 (en) * 2008-03-03 2012-08-28 Jpmorgan Chase Bank, N.A. Authentication system and method
US8639214B1 (en) * 2007-10-26 2014-01-28 Iwao Fujisaki Communication device
US8959360B1 (en) * 2012-09-10 2015-02-17 Google Inc. Voice authentication and command

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6076055A (en) 1997-05-27 2000-06-13 Ameritech Speaker verification method
US7260724B1 (en) * 1999-09-20 2007-08-21 Security First Corporation Context sensitive dynamic authentication in a cryptographic system
US7404086B2 (en) * 2003-01-24 2008-07-22 Ac Technology, Inc. Method and apparatus for biometric authentication
US7278028B1 (en) * 2003-11-05 2007-10-02 Evercom Systems, Inc. Systems and methods for cross-hatching biometrics with other identifying data
US8296573B2 (en) * 2004-04-06 2012-10-23 International Business Machines Corporation System and method for remote self-enrollment in biometric databases

Patent Citations (39)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5806040A (en) * 1994-01-04 1998-09-08 Itt Corporation Speed controlled telephone credit card verification system
US6014441A (en) * 1994-08-05 2000-01-11 Smart Tone Authentication, Inc. Method and system for generation of tone signals over a transmission channel
US5774837A (en) * 1995-09-13 1998-06-30 Voxware, Inc. Speech coding system and method using voicing probability determination
US5937381A (en) * 1996-04-10 1999-08-10 Itt Defense, Inc. System for voice verification of telephone transactions
US20030046083A1 (en) * 1996-11-22 2003-03-06 Edward J. Devinney User validation for information system access and transaction processing
US5933803A (en) * 1996-12-12 1999-08-03 Nokia Mobile Phones Limited Speech encoding at variable bit rate
US5940799A (en) * 1997-09-15 1999-08-17 Motorola, Inc. System and method for securing speech transactions
US5970446A (en) * 1997-11-25 1999-10-19 At&T Corp Selective noise/channel/coding models and recognizers for automatic speech recognition
US6107935A (en) * 1998-02-11 2000-08-22 International Business Machines Corporation Systems and methods for access filtering employing relaxed recognition constraints
US6272463B1 (en) * 1998-03-03 2001-08-07 Lernout & Hauspie Speech Products N.V. Multi-resolution system and method for speaker verification
US6694295B2 (en) * 1998-05-25 2004-02-17 Nokia Mobile Phones Ltd. Method and a device for recognizing speech
US6314401B1 (en) * 1998-05-29 2001-11-06 New York State Technology Enterprise Corporation Mobile voice verification system
US6141644A (en) * 1998-09-04 2000-10-31 Matsushita Electric Industrial Co., Ltd. Speaker verification and speaker identification based on eigenvoices
US6546369B1 (en) * 1999-05-05 2003-04-08 Nokia Corporation Text-based speech synthesis method containing synthetic speech comparisons and updates
US6393305B1 (en) * 1999-06-07 2002-05-21 Nokia Mobile Phones Limited Secure wireless communication user identification by voice recognition
US20050171771A1 (en) * 1999-08-23 2005-08-04 Matsushita Electric Industrial Co., Ltd. Apparatus and method for speech coding
US6401066B1 (en) * 1999-11-09 2002-06-04 West Teleservices Holding Company Automated third party verification system
US20050033581A1 (en) * 2001-02-16 2005-02-10 Foster Mark J. Dual compression voice recordation non-repudiation system
US20020194005A1 (en) * 2001-03-27 2002-12-19 Lahr Roy J. Head-worn, trimodal device to increase transcription accuracy in a voice recognition system and to process unvocalized speech
US6973575B2 (en) * 2001-04-05 2005-12-06 International Business Machines Corporation System and method for voice recognition password reset
US20020178359A1 (en) * 2001-04-26 2002-11-28 Markus Baumeister Just-in-time authentication of users of a digital home network
US20050096906A1 (en) * 2002-11-06 2005-05-05 Ziv Barzilay Method and system for verifying and enabling user access based on voice parameters
US20040101112A1 (en) * 2002-11-26 2004-05-27 Lite-On Technology Corporation Voice identification method for cellular phone and cellular phone with voiceprint password
US20040158723A1 (en) * 2003-02-06 2004-08-12 Root David C. Methods for providing high-integrity enrollments into biometric authentication databases
US7222072B2 (en) * 2003-02-13 2007-05-22 Sbc Properties, L.P. Bio-phonetic multi-phrase speaker identity verification
US7925887B2 (en) * 2003-05-19 2011-04-12 Intellirad Solutions Pty Ltd. Multi-parameter biometric authentication
US7828652B2 (en) * 2004-02-12 2010-11-09 Igt Player verification method and system for remote gaming terminals
US20070124144A1 (en) * 2004-05-27 2007-05-31 Johnson Richard G Synthesized interoperable communications
US7698566B1 (en) * 2004-07-12 2010-04-13 Sprint Spectrum L.P. Location-based voice-print authentication method and system
US20060020459A1 (en) * 2004-07-21 2006-01-26 Carter John A System and method for immigration tracking and intelligence
US20080208578A1 (en) * 2004-09-23 2008-08-28 Koninklijke Philips Electronics, N.V. Robust Speaker-Dependent Speech Recognition System
US20060212407A1 (en) * 2005-03-17 2006-09-21 Lyon Dennis B User authentication and secure transaction system
US7522060B1 (en) * 2005-04-25 2009-04-21 Anytransactions, Inc. Graduated sanction/progressive response system and method for automated monitoring, scheduling and notification
US20080140420A1 (en) * 2006-12-08 2008-06-12 Delta Electronics, Inc. Remote payment system
US8639214B1 (en) * 2007-10-26 2014-01-28 Iwao Fujisaki Communication device
US20090158423A1 (en) * 2007-12-14 2009-06-18 Symbol Technologies, Inc. Locking mobile device cradle
US8255971B1 (en) * 2008-03-03 2012-08-28 Jpmorgan Chase Bank, N.A. Authentication system and method
US20090247125A1 (en) * 2008-03-27 2009-10-01 Grant Calum Anders Mckay Method and system for controlling access of computer resources of mobile client facilities
US8959360B1 (en) * 2012-09-10 2015-02-17 Google Inc. Voice authentication and command

Also Published As

Publication number Publication date
US20140350938A1 (en) 2014-11-27
US20160012824A1 (en) 2016-01-14
US9142218B2 (en) 2015-09-22
US9812133B2 (en) 2017-11-07
US8504365B2 (en) 2013-08-06
US20180075851A1 (en) 2018-03-15
US20130317824A1 (en) 2013-11-28
US20090259468A1 (en) 2009-10-15
US9412382B2 (en) 2016-08-09
US8805685B2 (en) 2014-08-12

Similar Documents

Publication Publication Date Title
O'Gorman Comparing passwords, tokens, and biometrics for user authentication
Riva et al. Progressive authentication: deciding when to authenticate on mobile phones
KR100528328B1 (en) Method and apparatus for user authentication
US6111517A (en) Continuous video monitoring using face recognition for access control
US9129101B2 (en) Single-channel multi-factor authentication
US9917833B2 (en) System and method for speaker recognition on mobile devices
US6691089B1 (en) User configurable levels of security for a speaker verification system
US9747926B2 (en) Hotword recognition
US8630391B2 (en) Voice authentication system and method using a removable voice ID card
US8316239B2 (en) Decoding information to allow access to computerized systems
US6213391B1 (en) Portable system for personal identification based upon distinctive characteristics of the user
US7093298B2 (en) Apparatus and method for security object enhancement and management
JP4939121B2 (en) The method for sequential authentication using one or more error rate characterizing each security challenge, system, and program
Jain Biometric recognition: how do I know who you are?
US6580814B1 (en) System and method for compressing biometric models
US9799338B2 (en) Voice print identification portal
US8924285B2 (en) Building whitelists comprising voiceprints not associated with fraud and screening calls using a combination of a whitelist and blacklist
US20170324721A1 (en) Methods, Systems, and Products for Authenticating Users
US9524719B2 (en) Bio-phonetic multi-phrase speaker identity verification
US20120140993A1 (en) Secure biometric authentication from an insecure device
US8190437B2 (en) Speaker verification methods and apparatus
US20090276839A1 (en) Identity collection, verification and security access control system
Monrose et al. Using voice to generate cryptographic keys
US8255223B2 (en) User authentication by combining speaker verification and reverse turing test
US10083695B2 (en) Dialog-based voiceprint security for business transactions

Legal Events

Date Code Title Description
AS Assignment

Owner name: AT&T LABS, INC., TEXAS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SCHROETER, HORST;REEL/FRAME:039598/0495

Effective date: 20080321

AS Assignment

Owner name: AT&T INTELLECTUAL PROPERTY I, L.P., GEORGIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:AT&T LABS, INC.;REEL/FRAME:041049/0747

Effective date: 20160204

AS Assignment

Owner name: NUANCE COMMUNICATIONS, INC., MASSACHUSETTS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:AT&T INTELLECTUAL PROPERTY I, L.P.;REEL/FRAME:041504/0952

Effective date: 20161214

STCF Information on status: patent grant

Free format text: PATENTED CASE